© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73551
    Prev
    Next
    INDEX
    Explanations

    for, against, pro, anti

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pioneering
    -1.52
     specify
    -1.50
     bereits
    -1.43
    我跟
    -1.40
     pretentious
    -1.37
     I
    -1.33
     noteworthy
    -1.33
     Nachweis
    -1.30
    ’，
    -1.27
    thschild
    -1.26
    POSITIVE LOGITS
     exercices
    1.62
     查看
    1.49
     explications
    1.48
    :{}
    1.47
     bandou
    1.42
    ;
    1.42
    呖
    1.41
    </h1>
    1.38
     tranſ
    1.38
     giy
    1.38
    Activations Density 0.018%

    No Known Activations